Rethinking the Reverse-engineering of Trojan Triggers. (arXiv:2210.15127v1 [cs.CR])

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks.
Reverse-engineering methods can reconstruct the trigger and thus identify
affected models. Existing reverse-engineering methods only consider input space
constraints, e.g., trigger size in the input space. Expressly, they assume the
triggers are static patterns in the input space and fail to detect models with
feature space triggers such as image style transformations. We observe that
both input-space and feature-space Trojans are associated with feature space
hyperplanes. Based on this observation, …

engineering reverse trojan